Lithuanian startup launches open-source network to detect Shahed-type drones • Hacker News Board

Re: Lithuanian startup launches open-source network to detect Shahed-type drones

#61

Post by dghlsakjg » Sat, Jun 20, 2026, 3:43 PM UTC

energy123 wrote: post #60

dghlsakjg wrote: post #50

Earlier quoted context omitted.

Clouds and nighttime are a barrier to visual detection. Even with good effectiveness the conditions needed for that would mean that you have far less than 50% uptime, and your downtime is predictable to your adversary. A cheap radar takes an order of magnitude less power to run on hardware that is cheaper than an LLM and can see way farther than a camera.

Radar can't effectively see the new low-altitude small fiber optic spool first-person drones that are redefining frontline war. The solution is going to be multi-modal (optical + audio) and imperfect. The above poster is correct that an ordinary camera with computer vision (not an LLM, of course) is going to be part of the multimodal defense in depth. Shahed-type one-way attack drones are important to defend against,…

My comment was about Shaheds like the article we are commenting on.

for what you are talking about, audio is a great option

Re: Lithuanian startup launches open-source network to detect Shahed-type drones

#62

Post by lnsru » Sat, Jun 20, 2026, 3:46 PM UTC

rdtsc wrote: post #49

dghlsakjg wrote: post #42

Earlier quoted context omitted.

At those higher altitudes they are trivial for radar to detect, and from farther away too. They are adapting cheap commodity used marine radars to get this done in some places I suspect the Shaheds are going higher to mitigate AA ground fire. Higher up you have to send a missile or interceptor up. It’s a trade off.

And interceptors are more expensive than Shaheds. A $100k interceptor (guessing here) to shoot a $10k Shahed can be an acceptable deal for the side launching the Shaheds.

Reusable interceptor has BOM of 3000$, 15000$ sales price. Wanted to start this project with an ex-colleague, but he bought old house and is stuck trying to make it livable.

Anyone interested in cooperation? I am hardware and math guy.

Re: Lithuanian startup launches open-source network to detect Shahed-type drones

#63

Post by celsoazevedo » Sat, Jun 20, 2026, 3:46 PM UTC

dzhiurgis wrote: post #57

comrade1234 wrote: post #32

Earlier quoted context omitted.

[flagged]

[flagged]

I don't follow American politics that closely, but here in Europe, I don't remember ever seeing Merkel doing this:

- https://i.haasie.com/KeO.mp4

Can you please provide videos of them doing the same gesture?

Re: Lithuanian startup launches open-source network to detect Shahed-type drones

#64

Post by kklisura » Sat, Jun 20, 2026, 3:46 PM UTC

Neywiny wrote: post #28

warumdarum wrote: post #12

Earlier quoted context omitted.

So film the sky during charging and run a llm on it?

Or an image detection model. Fraction of the compute and can run even on edge embedded. And easy to train with your own data

Or something like this https://www.youtube.com/watch?v=YZkLQsv3huo

Re: Lithuanian startup launches open-source network to detect Shahed-type drones

#65

Post by embedding-shape » Sat, Jun 20, 2026, 3:47 PM UTC

quietbritishjim wrote: post #44

embedding-shape wrote: post #31

Earlier quoted context omitted.

"Unwanted traffic", is what I go by typically. What is your understanding (if you have one) of that term?

Spam specifically means (at least originally) so much unwanted traffic that it overwhelms legitimate traffic. So can I see why that commenter might have considered it a contradiction to say "the majority being truthful" as a strategy to deal with spam. The name comes from a Monty Python sketch where "SPAM!" is being sung so loudly that it drowned out any other conservation.

> Spam specifically means (at least originally) so much unwanted traffic that it overwhelms legitimate traffic.

I guess what today is more commonly known as DOS (or even DDOS sometimes, even if it isn't actually "distributed" per se, for some reason).

I did know about the name since before, but not the original meaning, so cheers for the explanation :)

Re: Lithuanian startup launches open-source network to detect Shahed-type drones

#66

Post by energy123 » Sat, Jun 20, 2026, 3:49 PM UTC

rdtsc wrote: post #49

dghlsakjg wrote: post #42

Earlier quoted context omitted.

At those higher altitudes they are trivial for radar to detect, and from farther away too. They are adapting cheap commodity used marine radars to get this done in some places I suspect the Shaheds are going higher to mitigate AA ground fire. Higher up you have to send a missile or interceptor up. It’s a trade off.

And interceptors are more expensive than Shaheds. A $100k interceptor (guessing here) to shoot a $10k Shahed can be an acceptable deal for the side launching the Shaheds.

A $100k interceptor to save a $10 million critical facility against a $10k Shahed is a bargain. You saved $9.9 million dollars.

Interceptor economics makes more sense when you reason about the bigger picture. The point is to buy you time to remove the supply chain and the stocks so that you're not trading 1:1 forever. It's a stop-gap, or at least it's supposed to be.

However that only works in a war where you have air and informational superiority. In a peer-like conflict with information asymmetries and air parity (no way to remove the opponent's industrial base), such as Ukraine-Russia, the intercept economics are less appealing.

Re: Lithuanian startup launches open-source network to detect Shahed-type drones

#67

Post by MobiusHorizons » Sat, Jun 20, 2026, 3:50 PM UTC

energy123 wrote: post #60

dghlsakjg wrote: post #50

Earlier quoted context omitted.

Clouds and nighttime are a barrier to visual detection. Even with good effectiveness the conditions needed for that would mean that you have far less than 50% uptime, and your downtime is predictable to your adversary. A cheap radar takes an order of magnitude less power to run on hardware that is cheaper than an LLM and can see way farther than a camera.

Radar can't effectively see the new low-altitude small fiber optic spool first-person drones that are redefining frontline war. The solution is going to be multi-modal (optical + audio) and imperfect. The above poster is correct that an ordinary camera with computer vision (not an LLM, of course) is going to be part of the multimodal defense in depth. Shahed-type one-way attack drones are important to defend against,…

The article and this thread are about shaheed style drones.

As far as I know, stopping fiber optic fpv drones leans more on physical barriers that catch the fiber (eg road nets) rather than trying to detect and destroy the drone. It’s usually too late by the time you can hear or see a drone that size.

Re: Lithuanian startup launches open-source network to detect Shahed-type drones

#68

Post by energy123 » Sat, Jun 20, 2026, 3:52 PM UTC

MobiusHorizons wrote: post #67

energy123 wrote: post #60

Earlier quoted context omitted.

Radar can't effectively see the new low-altitude small fiber optic spool first-person drones that are redefining frontline war. The solution is going to be multi-modal (optical + audio) and imperfect. The above poster is correct that an ordinary camera with computer vision (not an LLM, of course) is going to be part of the multimodal defense in depth. Shahed-type one-way attack drones are important to defend against,…

The article and this thread are about shaheed style drones. As far as I know, stopping fiber optic fpv drones leans more on physical barriers that catch the fiber (eg road nets) rather than trying to detect and destroy the drone. It’s usually too late by the time you can hear or see a drone that size.

> It’s usually too late by the time you can hear or see a drone that size.

What does the asymptote looks like as defender and aggressor keep iterating. Who has the advantage? Can optical technology get so good at detecting (at least when it isn't raining) that eventually the balance shifts in favor of the defender?

Re: Lithuanian startup launches open-source network to detect Shahed-type drones

#69

Post by ruined » Sat, Jun 20, 2026, 3:54 PM UTC

lnsru wrote: post #62

rdtsc wrote: post #49

Earlier quoted context omitted.

And interceptors are more expensive than Shaheds. A $100k interceptor (guessing here) to shoot a $10k Shahed can be an acceptable deal for the side launching the Shaheds.

Reusable interceptor has BOM of 3000$, 15000$ sales price. Wanted to start this project with an ex-colleague, but he bought old house and is stuck trying to make it livable. Anyone interested in cooperation? I am hardware and math guy.

maybe this is a stupid question but how could you possibly re-use a thing that explodes in use

Re: Lithuanian startup launches open-source network to detect Shahed-type drones

#70

Post by lnsru » Sat, Jun 20, 2026, 3:57 PM UTC

Or it is a public stunt? I am naysayer engineer. Build acoustic detection system for anomaly detection in manufacturing line. It worked with studio level equipment with lots of noise filtering measures. First challenge was to have microphone listening to the right place and getting reliable signal. Second challenge was to amplify the right signal to a level where the features could be extracted. I doubt an old android with dirty microphone can detect anything reliably.